INDEX

Explanations

references to computer science terms or people

oai_token-act-pair · gpt-3.5-turbo

references to computer-related subjects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eca

-0.79

¿½

-0.76

abouts

-0.75

raints

-0.71

ctr

-0.70

 Parables

-0.70

 Hodg

-0.68

 Krug

-0.65

 Hollow

-0.65

eter

-0.64

POSITIVE LOGITS

ized

1.17

izable

1.00

ization

0.98

isation

0.95

ised

0.94

 science

0.91

izes

0.91

 readable

0.90

 programmer

0.89

 aided

0.87

Activations Density 0.039%

references to computer science terms or people

references to computer-related subjects

No Comments

No Known Activations